Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91578e82842d027063df305fb222c3430a8309c1bb9ba24f8f1745b599e30951
+oid sha256:deefedb77f3f16adeafd76f749a4061d114ecca510fb0b1f004f772c7c068f36
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfee9f76e0df641bc2f916d0cddcee4f4d58d6713aa3f69217499455cb3570b
+oid sha256:3d84c2bddf6f7d3d1f3baaf9cad6c887d1e6116a62cc4c4e24b64c772c8994ac
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa41af9a9131c8a34c7fa26a174afe8e5249c6e51067f58f674ef3df9ef55a84
+oid sha256:cce298c7cacb1b98db3d5b0ddd48d2de024523ffef2cde0bba50e43a229ea675
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a96694ef1c815118714d622251a7fe78bb4f4edaba937e971bb45aa4d935e8
+oid sha256:f9954d6173e982fe7b54b0ef84ee89e4af6ef602ede332a81962b399a9f3687b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c460e389c2cd1aa89788865fc4ed01e1cc97b85a958d6e69797c55ade31f55e
+oid sha256:eab6c30041e2cad68443fee6c73e9c380ceebecb40ec14f4392b2dda8ca54877
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1271cfb39072e835debe31b3638071faf2bddf24e110c1137e2088faa8376472
+oid sha256:d9ff5b0a91a4e8dd61c630a20e15ef6e23bdceea27ee5503243a382beea7526e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1890558004379272,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01272993444083763,
+  "best_metric": 1.1442079544067383,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02545986888167526,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 27.366,
       "eval_steps_per_second": 7.115,
       "step": 25
+    },
+    {
+      "epoch": 0.013239131818471134,
+      "grad_norm": 0.26080581545829773,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.42,
+      "step": 26
+    },
+    {
+      "epoch": 0.01374832919610464,
+      "grad_norm": 0.3292554020881653,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1536,
+      "step": 27
+    },
+    {
+      "epoch": 0.014257526573738145,
+      "grad_norm": 0.4155060052871704,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8953,
+      "step": 28
+    },
+    {
+      "epoch": 0.01476672395137165,
+      "grad_norm": 0.2531004548072815,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3548,
+      "step": 29
+    },
+    {
+      "epoch": 0.015275921329005156,
+      "grad_norm": 0.23809029161930084,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2107,
+      "step": 30
+    },
+    {
+      "epoch": 0.01578511870663866,
+      "grad_norm": 0.21378874778747559,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2265,
+      "step": 31
+    },
+    {
+      "epoch": 0.016294316084272165,
+      "grad_norm": 0.23385454714298248,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3131,
+      "step": 32
+    },
+    {
+      "epoch": 0.016803513461905673,
+      "grad_norm": 0.24048176407814026,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3234,
+      "step": 33
+    },
+    {
+      "epoch": 0.017312710839539176,
+      "grad_norm": 0.2692112326622009,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2975,
+      "step": 34
+    },
+    {
+      "epoch": 0.01782190821717268,
+      "grad_norm": 0.29762008786201477,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2839,
+      "step": 35
+    },
+    {
+      "epoch": 0.018331105594806187,
+      "grad_norm": 0.327226459980011,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2363,
+      "step": 36
+    },
+    {
+      "epoch": 0.01884030297243969,
+      "grad_norm": 0.4358674883842468,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2147,
+      "step": 37
+    },
+    {
+      "epoch": 0.019349500350073198,
+      "grad_norm": 0.34083041548728943,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3163,
+      "step": 38
+    },
+    {
+      "epoch": 0.019858697727706702,
+      "grad_norm": 0.22418354451656342,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3162,
+      "step": 39
+    },
+    {
+      "epoch": 0.02036789510534021,
+      "grad_norm": 0.20082779228687286,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.1048,
+      "step": 40
+    },
+    {
+      "epoch": 0.020877092482973713,
+      "grad_norm": 0.1930985152721405,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2333,
+      "step": 41
+    },
+    {
+      "epoch": 0.021386289860607217,
+      "grad_norm": 0.2139016091823578,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3156,
+      "step": 42
+    },
+    {
+      "epoch": 0.021895487238240724,
+      "grad_norm": 0.1971304565668106,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1132,
+      "step": 43
+    },
+    {
+      "epoch": 0.022404684615874228,
+      "grad_norm": 0.20899564027786255,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.342,
+      "step": 44
+    },
+    {
+      "epoch": 0.022913881993507735,
+      "grad_norm": 0.2296018749475479,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.3284,
+      "step": 45
+    },
+    {
+      "epoch": 0.02342307937114124,
+      "grad_norm": 0.2295154631137848,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3326,
+      "step": 46
+    },
+    {
+      "epoch": 0.023932276748774742,
+      "grad_norm": 0.2735446095466614,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.2638,
+      "step": 47
+    },
+    {
+      "epoch": 0.02444147412640825,
+      "grad_norm": 0.29943835735321045,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2214,
+      "step": 48
+    },
+    {
+      "epoch": 0.024950671504041753,
+      "grad_norm": 0.37347203493118286,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2436,
+      "step": 49
+    },
+    {
+      "epoch": 0.02545986888167526,
+      "grad_norm": 0.5929493308067322,
+      "learning_rate": 1e-05,
+      "loss": 1.0478,
+      "step": 50
+    },
+    {
+      "epoch": 0.02545986888167526,
+      "eval_loss": 1.1442079544067383,
+      "eval_runtime": 1.8425,
+      "eval_samples_per_second": 27.137,
+      "eval_steps_per_second": 7.056,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null